On the Information Processing of One-Dimensional Wasserstein Distances with Finite Samples
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915621708496896 |
|---|---|
| author | Jang, Cheongjae Won, Jonghyun Jun, Soyeon Chung, Chun Kee Joo, Keehyoung Noh, Yung-Kyun |
| author_facet | Jang, Cheongjae Won, Jonghyun Jun, Soyeon Chung, Chun Kee Joo, Keehyoung Noh, Yung-Kyun |
| contents | Leveraging the Wasserstein distance -- a summation of sample-wise transport distances in data space -- is advantageous in many applications for measuring support differences between two underlying density functions. However, when supports significantly overlap while densities exhibit substantial pointwise differences, it remains unclear whether and how this transport information can accurately identify these differences, particularly their analytic characterization in finite-sample settings. We address this issue by conducting an analysis of the information processing capabilities of the one-dimensional Wasserstein distance with finite samples. By utilizing the Poisson process and isolating the rate factor, we demonstrate the capability of capturing the pointwise density difference with Wasserstein distances and how this information harmonizes with support differences. The analyzed properties are confirmed using neural spike train decoding and amino acid contact frequency data. The results reveal that the one-dimensional Wasserstein distance highlights meaningful density differences related to both rate and support. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12881 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On the Information Processing of One-Dimensional Wasserstein Distances with Finite Samples Jang, Cheongjae Won, Jonghyun Jun, Soyeon Chung, Chun Kee Joo, Keehyoung Noh, Yung-Kyun Machine Learning Leveraging the Wasserstein distance -- a summation of sample-wise transport distances in data space -- is advantageous in many applications for measuring support differences between two underlying density functions. However, when supports significantly overlap while densities exhibit substantial pointwise differences, it remains unclear whether and how this transport information can accurately identify these differences, particularly their analytic characterization in finite-sample settings. We address this issue by conducting an analysis of the information processing capabilities of the one-dimensional Wasserstein distance with finite samples. By utilizing the Poisson process and isolating the rate factor, we demonstrate the capability of capturing the pointwise density difference with Wasserstein distances and how this information harmonizes with support differences. The analyzed properties are confirmed using neural spike train decoding and amino acid contact frequency data. The results reveal that the one-dimensional Wasserstein distance highlights meaningful density differences related to both rate and support. |
| title | On the Information Processing of One-Dimensional Wasserstein Distances with Finite Samples |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.12881 |